Merge remote-tracking branch '4.9/tmp-77d3588' into 4.9

* 4.9/tmp-77d3588:
  Linux 4.9.31
  xfs: Fix off-by-in in loop termination in xfs_find_get_desired_pgoff()
  xfs: fix unaligned access in xfs_btree_visit_blocks
  xfs: avoid mount-time deadlock in CoW extent recovery
  xfs: xfs_trans_alloc_empty
  xfs: bad assertion for delalloc an extent that start at i_size
  xfs: BMAPX shouldn't barf on inline-format directories
  xfs: fix indlen accounting error on partial delalloc conversion
  xfs: fix use-after-free in xfs_finish_page_writeback
  xfs: reserve enough blocks to handle btree splits when remapping
  xfs: wait on new inodes during quotaoff dquot release
  xfs: update ag iterator to support wait on new inodes
  xfs: support ability to wait on new inodes
  xfs: fix up quotacheck buffer list error handling
  xfs: prevent multi-fsb dir readahead from reading random blocks
  xfs: handle array index overrun in xfs_dir2_leaf_readbuf()
  xfs: fix integer truncation in xfs_bmap_remap_alloc
  xfs: drop iolock from reclaim context to appease lockdep
  xfs: actually report xattr extents via iomap
  xfs: fix over-copying of getbmap parameters from userspace
  xfs: use dedicated log worker wq to avoid deadlock with cil wq
  xfs: fix kernel memory exposure problems
  xfs: rework the inline directory verifiers
  xfs: verify inline directory data forks
  xfs: fix off-by-one on max nr_pages in xfs_find_get_desired_pgoff()
  xfs: use ->b_state to fix buffer I/O accounting release race
  xfs: Fix missed holes in SEEK_HOLE implementation
  drm/gma500/psb: Actually use VBT mode when it is found
  mm/slub.c: trace free objects at KERN_INFO
  slub/memcg: cure the brainless abuse of sysfs attributes
  ksm: prevent crash after write_protect_page fails
  x86/boot: Use CROSS_COMPILE prefix for readelf
  RDMA/qib,hfi1: Fix MR reference count leak on write with immediate
  mm: consider memblock reservations for deferred memory initialization sizing
  mlock: fix mlock count can not decrease in race condition
  mm/migrate: fix refcount handling when !hugepage_migration_supported()
  ALSA: hda - apply STAC_9200_DELL_M22 quirk for Dell Latitude D430
  pcmcia: remove left-over %Z format
  drm/radeon: Fix vram_size/visible values in DRM_RADEON_GEM_INFO ioctl
  drm/radeon: Unbreak HPD handling for r600+
  drm/radeon/ci: disable mclk switching for high refresh rates (v2)
  scsi: mpt3sas: Force request partial completion alignment
  nvme: avoid to use blk_mq_abort_requeue_list()
  nvme: use blk_mq_start_hw_queues() in nvme_kill_queues()
  nvme-rdma: support devices with queue size < 32
  HID: wacom: Have wacom_tpc_irq guard against possible NULL dereference
  ibmvscsis: Fix the incorrect req_lim_delta
  ibmvscsis: Clear left-over abort_cmd pointers
  iscsi-target: Always wait for kthread_should_stop() before kthread exit
  mmc: sdhci-iproc: suppress spurious interrupt with Multiblock read
  Revert "ACPI / button: Change default behavior to lid_init_state=open"
  acpi, nfit: Fix the memory error check in nfit_handle_mce()
  x86/MCE: Export memory_error()
  crypto: skcipher - Add missing API setkey checks
  i2c: i2c-tiny-usb: fix buffer not being DMA capable
  drivers/tty: 8250: only call fintek_8250_probe when doing port I/O
  powerpc/spufs: Fix hash faults for kernel regions
  fs/ufs: Set UFS default maximum bytes per file
  sparc/ftrace: Fix ftrace graph time measurement
  sparc: Fix -Wstringop-overflow warning
  bpf: add bpf_clone_redirect to bpf_helper_changes_pkt_data
  ipv4: add reference counting to metrics
  sctp: fix ICMP processing if skb is non-linear
  tcp: avoid fastopen API to be used on AF_UNSPEC
  virtio-net: enable TSO/checksum offloads for Q-in-Q vlans
  be2net: Fix offload features for Q-in-Q packets
  vlan: Fix tcp checksum offloads in Q-in-Q vlans
  net: phy: marvell: Limit errata to 88m1101
  net/mlx5: Avoid using pending command interface slots
  bonding: fix accounting of active ports in 3ad
  ipv6: fix out of bound writes in __ip6_append_data()
  bridge: start hello_timer when enabling KERNEL_STP in br_stp_start
  qmi_wwan: add another Lenovo EM74xx device ID
  bridge: netlink: check vlan_default_pvid range
  ipv6: Check ip6_find_1stfragopt() return value properly.
  ipv6: Prevent overrun when parsing v6 header options
  net: Improve handling of failures on link and route dumps
  tcp: eliminate negative reordering in tcp_clean_rtx_queue
  net/mlx5e: Fix ethtool pause support and advertise reporting
  net/mlx5e: Use the correct pause values for ethtool advertising
  net/packet: fix missing net_device reference release
  sctp: do not inherit ipv6_{mc|ac|fl}_list from parent
  sctp: fix src address selection if using secondary addresses for ipv6
  tcp: avoid fragmenting peculiar skbs in SACK
  net: fix compile error in skb_orphan_partial()
  netem: fix skb_orphan_partial()
  bpf, arm64: fix faulty emission of map access in tail calls
  s390/qeth: add missing hash table initializations
  s390/qeth: avoid null pointer dereference on OSN
  s390/qeth: unbreak OSM and OSN support
  s390/qeth: handle sysfs error during initialization
  ipv6/dccp: do not inherit ipv6_mc_list from parent
  driver: vrf: Fix one possible use-after-free issue
  dccp/tcp: do not inherit mc_list from parent
  android: base-cfg: disable CONFIG_NFSD and CONFIG_NFS_FS
  UPSTREAM: drm/ttm: fix ttm_bo_wait
  FROMLIST: [net-next,v2,2/2] bpf: Remove the capability check for cgroup skb eBPF program
  FROMLIST: [net-next,v2,1/2] bpf: Allow CGROUP_SKB eBPF program to access sk_buff
  ANDROID: Update init/do_mounts_dm.c to the latest ChromiumOS version.
  FROMLIST: f2fs: sanity check size of nat and sit cache
  FROMLIST: f2fs: sanity check checkpoint segno and blkoff
  ANDROID: Kconfig: add depends for UID_SYS_STATS
  ANDROID: hid: uhid: implement refcount for open and close
  ANDROID: cpufreq: system panic when switch interactive governor frequently
  ANDROID: sched/walt: kill {min,max}_capacity
  ANDROID: fixup! sched/fair: jump to max OPP when crossing UP threshold
  BACKPORT [FROMLIST] New getsockopt option to get socket cookie
  UPSTREAM: bpf: cgroup: fix documentation of __cgroup_bpf_update()
  BACKPORT: bpf: introduce BPF_F_ALLOW_OVERRIDE flag
  UPSTREAM: bpf: restore skb->sk before pskb_trim() call
  UPSTREAM: cgroup: move CONFIG_SOCK_CGROUP_DATA to init/Kconfig
  UPSTREAM: cgroup, bpf: remove unnecessary #include
  ANDROID: mnt: Fix next_descendent

Conflicts:
	drivers/cpufreq/cpufreq_interactive.c
	init/do_mounts_dm.c
	kernel/sched/core.c
	kernel/sched/walt.c

Change-Id: I7a987967400f81c9d2ec2dc2283a881de9fd386f
Signed-off-by: Kyle Yan <kyan@codeaurora.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 30
+SUBLEVEL = 31
 EXTRAVERSION =
 NAME = Roaring Lionus
 

arch/alpha/include/uapi/asm/socket.h

@@ -97,4 +97,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _UAPI_ASM_SOCKET_H */

arch/arm64/net/bpf_jit_comp.c

@@ -252,8 +252,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	off = offsetof(struct bpf_array, ptrs);
 	emit_a64_mov_i64(tmp, off, ctx);
-	emit(A64_LDR64(tmp, r2, tmp), ctx);
-	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_ADD(1, tmp, r2, tmp), ctx);
+	emit(A64_LSL(1, prg, r3, 3), ctx);
+	emit(A64_LDR64(prg, tmp, prg), ctx);
 	emit(A64_CBZ(1, prg, jmp_offset), ctx);
 
 	/* goto *(prog->bpf_func + prologue_size); */

arch/avr32/include/uapi/asm/socket.h

@@ -90,4 +90,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */

arch/frv/include/uapi/asm/socket.h

@@ -90,5 +90,7 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _ASM_SOCKET_H */
 

arch/ia64/include/uapi/asm/socket.h

@@ -99,4 +99,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _ASM_IA64_SOCKET_H */

arch/m32r/include/uapi/asm/socket.h

@@ -90,4 +90,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _ASM_M32R_SOCKET_H */

arch/mips/include/uapi/asm/socket.h

@@ -108,4 +108,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _UAPI_ASM_SOCKET_H */

arch/mn10300/include/uapi/asm/socket.h

@@ -90,4 +90,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _ASM_SOCKET_H */

arch/parisc/include/uapi/asm/socket.h

@@ -89,4 +89,6 @@
 
 #define SO_CNX_ADVICE		0x402E
 
+#define SO_COOKIE		0x4032
+
 #endif /* _UAPI_ASM_SOCKET_H */

arch/powerpc/include/uapi/asm/socket.h

@@ -97,4 +97,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif	/* _ASM_POWERPC_SOCKET_H */

arch/powerpc/platforms/cell/spu_base.c

@@ -197,7 +197,9 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 	    (REGION_ID(ea) != USER_REGION_ID)) {
 
 		spin_unlock(&spu->register_lock);
-		ret = hash_page(ea, _PAGE_PRESENT | _PAGE_READ, 0x300, dsisr);
+		ret = hash_page(ea,
+				_PAGE_PRESENT | _PAGE_READ | _PAGE_PRIVILEGED,
+				0x300, dsisr);
 		spin_lock(&spu->register_lock);
 
 		if (!ret) {

arch/s390/include/uapi/asm/socket.h

@@ -96,4 +96,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif /* _ASM_SOCKET_H */

arch/sparc/include/asm/pgtable_32.h

@@ -91,9 +91,9 @@ extern unsigned long pfn_base;
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
-#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
 /*
  * In general all page table modifications should use the V8 atomic

arch/sparc/include/asm/setup.h

@@ -16,7 +16,7 @@ extern char reboot_command[];
  */
 extern unsigned char boot_cpu_id;
 
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 extern int serial_console;
 static inline int con_is_present(void)

arch/sparc/include/uapi/asm/socket.h

@@ -86,6 +86,8 @@
 
 #define SO_CNX_ADVICE		0x0037
 
+#define SO_COOKIE		0x003b
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002

arch/sparc/kernel/ftrace.c

@@ -130,18 +130,17 @@ unsigned long prepare_ftrace_return(unsigned long parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return parent + 8UL;
 
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace))
+		return parent + 8UL;
+
 	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
 				     frame_pointer, NULL) == -EBUSY)
 		return parent + 8UL;
 
-	trace.func = self_addr;
-
-	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
-		return parent + 8UL;
-	}
-
 	return return_hooker;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */

arch/sparc/mm/init_32.c

@@ -301,7 +301,7 @@ void __init mem_init(void)
 
 
 	/* Saves us work later. */
-	memset((void *)&empty_zero_page, 0, PAGE_SIZE);
+	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 
 	i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5);
 	i += 1;

arch/x86/boot/compressed/Makefile

@@ -94,7 +94,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 quiet_cmd_check_data_rel = DATAREL $@
 define cmd_check_data_rel
 	for obj in $(filter %.o,$^); do \
-		readelf -S $$obj | grep -qF .rel.local && { \
+		${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \
 			echo "error: $$obj has data relocations!" >&2; \
 			exit 1; \
 		} || true; \

arch/x86/include/asm/mce.h

@@ -257,6 +257,7 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
 #endif
 
 int mce_available(struct cpuinfo_x86 *c);
+bool mce_is_memory_error(struct mce *m);
 
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);

arch/x86/kernel/cpu/mcheck/mce.c

@@ -598,16 +598,14 @@ static void mce_read_aux(struct mce *m, int i)
 	}
 }
 
-static bool memory_error(struct mce *m)
+bool mce_is_memory_error(struct mce *m)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	if (c->x86_vendor == X86_VENDOR_AMD) {
+	if (m->cpuvendor == X86_VENDOR_AMD) {
 		/* ErrCodeExt[20:16] */
 		u8 xec = (m->status >> 16) & 0x1f;
 
 		return (xec == 0x0 || xec == 0x8);
-	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
+	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
 		 *
@@ -628,6 +626,7 @@ static bool memory_error(struct mce *m)
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
@@ -691,7 +690,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 		severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
 
-		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
+		if (severity == MCE_DEFERRED_SEVERITY && mce_is_memory_error(&m))
 			if (m.status & MCI_STATUS_ADDRV)
 				m.severity = severity;
 

arch/xtensa/include/uapi/asm/socket.h

@@ -101,4 +101,6 @@
 
 #define SO_CNX_ADVICE		53
 
+#define SO_COOKIE		57
+
 #endif	/* _XTENSA_SOCKET_H */

crypto/skcipher.c

@@ -221,6 +221,44 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
 	return 0;
 }
 
+static int skcipher_setkey_unaligned(struct crypto_skcipher *tfm,
+				     const u8 *key, unsigned int keylen)
+{
+	unsigned long alignmask = crypto_skcipher_alignmask(tfm);
+	struct skcipher_alg *cipher = crypto_skcipher_alg(tfm);
+	u8 *buffer, *alignbuffer;
+	unsigned long absize;
+	int ret;
+
+	absize = keylen + alignmask;
+	buffer = kmalloc(absize, GFP_ATOMIC);
+	if (!buffer)
+		return -ENOMEM;
+
+	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
+	memcpy(alignbuffer, key, keylen);
+	ret = cipher->setkey(tfm, alignbuffer, keylen);
+	kzfree(buffer);
+	return ret;
+}
+
+static int skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	struct skcipher_alg *cipher = crypto_skcipher_alg(tfm);
+	unsigned long alignmask = crypto_skcipher_alignmask(tfm);
+
+	if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) {
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	if ((unsigned long)key & alignmask)
+		return skcipher_setkey_unaligned(tfm, key, keylen);
+
+	return cipher->setkey(tfm, key, keylen);
+}
+
 static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
@@ -241,7 +279,7 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 	    tfm->__crt_alg->cra_type == &crypto_givcipher_type)
 		return crypto_init_skcipher_ops_ablkcipher(tfm);
 
-	skcipher->setkey = alg->setkey;
+	skcipher->setkey = skcipher_setkey;
 	skcipher->encrypt = alg->encrypt;
 	skcipher->decrypt = alg->decrypt;
 	skcipher->ivsize = alg->ivsize;

drivers/acpi/button.c

@@ -113,7 +113,7 @@ struct acpi_button {
 
 static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
 static struct acpi_device *lid_device;
-static u8 lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
+static u8 lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
 
 static unsigned long lid_report_interval __read_mostly = 500;
 module_param(lid_report_interval, ulong, 0644);

drivers/acpi/nfit/mce.c

@@ -26,7 +26,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 	struct nfit_spa *nfit_spa;
 
 	/* We only care about memory errors */
-	if (!(mce->status & MCACOD))
+	if (!mce_is_memory_error(mce))
 		return NOTIFY_DONE;
 
 	/*

drivers/char/pcmcia/cm4040_cs.c

@@ -374,7 +374,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 
 	rc = write_sync_reg(SCR_HOST_TO_READER_START, dev);
 	if (rc <= 0) {
-		DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+		DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
 		DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 		if (rc == -ERESTARTSYS)
 			return rc;
@@ -387,7 +387,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	for (i = 0; i < bytes_to_write; i++) {
 		rc = wait_for_bulk_out_ready(dev);
 		if (rc <= 0) {
-			DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2Zx\n",
+			DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2zx\n",
 			       rc);
 			DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 			if (rc == -ERESTARTSYS)
@@ -403,7 +403,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	rc = write_sync_reg(SCR_HOST_TO_READER_DONE, dev);
 
 	if (rc <= 0) {
-		DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+		DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
 		DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 		if (rc == -ERESTARTSYS)
 			return rc;

drivers/gpu/drm/gma500/psb_intel_lvds.c

@@ -774,20 +774,23 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		if (scan->type & DRM_MODE_TYPE_PREFERRED) {
 			mode_dev->panel_fixed_mode =
 			    drm_mode_duplicate(dev, scan);
+			DRM_DEBUG_KMS("Using mode from DDC\n");
 			goto out;	/* FIXME: check for quirks */
 		}
 	}
 
 	/* Failed to get EDID, what about VBT? do we need this? */
-	if (mode_dev->vbt_mode)
+	if (dev_priv->lfp_lvds_vbt_mode) {
 		mode_dev->panel_fixed_mode =
-		    drm_mode_duplicate(dev, mode_dev->vbt_mode);
+			drm_mode_duplicate(dev, dev_priv->lfp_lvds_vbt_mode);
 
-	if (!mode_dev->panel_fixed_mode)
-		if (dev_priv->lfp_lvds_vbt_mode)
-			mode_dev->panel_fixed_mode =
-				drm_mode_duplicate(dev,
-					dev_priv->lfp_lvds_vbt_mode);
+		if (mode_dev->panel_fixed_mode) {
+			mode_dev->panel_fixed_mode->type |=
+				DRM_MODE_TYPE_PREFERRED;
+			DRM_DEBUG_KMS("Using mode from VBT\n");
+			goto out;
+		}
+	}
 
 	/*
 	 * If we didn't get EDID, try checking if the panel is already turned
@@ -804,6 +807,7 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		if (mode_dev->panel_fixed_mode) {
 			mode_dev->panel_fixed_mode->type |=
 			    DRM_MODE_TYPE_PREFERRED;
+			DRM_DEBUG_KMS("Using pre-programmed mode\n");
 			goto out;	/* FIXME: check for quirks */
 		}
 	}

drivers/gpu/drm/radeon/ci_dpm.c

@@ -776,6 +776,12 @@ bool ci_dpm_vblank_too_short(struct radeon_device *rdev)
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
 	u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+        * blanking period would allow it
+        */
+	if (r600_dpm_get_vrefresh(rdev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else

drivers/gpu/drm/radeon/cik.c

@@ -7416,7 +7416,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -7446,7 +7446,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}

drivers/gpu/drm/radeon/evergreen.c

@@ -4933,7 +4933,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -4964,7 +4964,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}

drivers/gpu/drm/radeon/r600.c

@@ -3995,7 +3995,7 @@ static void r600_irq_ack(struct radeon_device *rdev)
 			WREG32(DC_HPD5_INT_CONTROL, tmp);
 		}
 		if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) {
-			tmp = RREG32(DC_HPD5_INT_CONTROL);
+			tmp = RREG32(DC_HPD6_INT_CONTROL);
 			tmp |= DC_HPDx_INT_ACK;
 			WREG32(DC_HPD6_INT_CONTROL, tmp);
 		}

drivers/gpu/drm/radeon/radeon_drv.c

@@ -97,9 +97,10 @@
  *   2.46.0 - Add PFP_SYNC_ME support on evergreen
  *   2.47.0 - Add UVD_NO_OP register support
  *   2.48.0 - TA_CS_BC_BASE_ADDR allowed on SI
+ *   2.49.0 - DRM_RADEON_GEM_INFO ioctl returns correct vram_size/visible values
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	48
+#define KMS_DRIVER_MINOR	49
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);

drivers/gpu/drm/radeon/radeon_gem.c

@@ -220,8 +220,8 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data,
 
 	man = &rdev->mman.bdev.man[TTM_PL_VRAM];
 
-	args->vram_size = rdev->mc.real_vram_size;
-	args->vram_visible = (u64)man->size << PAGE_SHIFT;
+	args->vram_size = (u64)man->size << PAGE_SHIFT;
+	args->vram_visible = rdev->mc.visible_vram_size;
 	args->vram_visible -= rdev->vram_pin_size;
 	args->gart_size = rdev->mc.gtt_size;
 	args->gart_size -= rdev->gart_pin_size;

drivers/gpu/drm/radeon/si.c

@@ -6330,7 +6330,7 @@ static inline void si_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -6361,7 +6361,7 @@ static inline void si_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}

drivers/gpu/drm/ttm/ttm_bo.c

@@ -1602,7 +1602,14 @@ EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool interruptible, bool no_wait)
 {
-	long timeout = no_wait ? 0 : 15 * HZ;
+	long timeout = 15 * HZ;
+
+	if (no_wait) {
+		if (reservation_object_test_signaled_rcu(bo->resv, true))
+			return 0;
+		else
+			return -EBUSY;
+	}
 
 	timeout = reservation_object_wait_timeout_rcu(bo->resv, true,
 						      interruptible, timeout);

drivers/hid/uhid.c

@@ -28,6 +28,8 @@
 #define UHID_NAME	"uhid"
 #define UHID_BUFSIZE	32
 
+static DEFINE_MUTEX(uhid_open_mutex);
+
 struct uhid_device {
 	struct mutex devlock;
 	bool running;
@@ -142,15 +144,26 @@ static void uhid_hid_stop(struct hid_device *hid)
 static int uhid_hid_open(struct hid_device *hid)
 {
 	struct uhid_device *uhid = hid->driver_data;
+	int retval = 0;
 
-	return uhid_queue_event(uhid, UHID_OPEN);
+	mutex_lock(&uhid_open_mutex);
+	if (!hid->open++) {
+		retval = uhid_queue_event(uhid, UHID_OPEN);
+		if (retval)
+			hid->open--;
+	}
+	mutex_unlock(&uhid_open_mutex);
+	return retval;
 }
 
 static void uhid_hid_close(struct hid_device *hid)
 {
 	struct uhid_device *uhid = hid->driver_data;
 
-	uhid_queue_event(uhid, UHID_CLOSE);
+	mutex_lock(&uhid_open_mutex);
+	if (!--hid->open)
+		uhid_queue_event(uhid, UHID_CLOSE);
+	mutex_unlock(&uhid_open_mutex);
 }
 
 static int uhid_hid_parse(struct hid_device *hid)

drivers/hid/wacom_wac.c

@@ -1400,37 +1400,38 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 {
 	unsigned char *data = wacom->data;
 
-	if (wacom->pen_input)
+	if (wacom->pen_input) {
 		dev_dbg(wacom->pen_input->dev.parent,
 			"%s: received report #%d\n", __func__, data[0]);
-	else if (wacom->touch_input)
+
+		if (len == WACOM_PKGLEN_PENABLED ||
+		    data[0] == WACOM_REPORT_PENABLED)
+			return wacom_tpc_pen(wacom);
+	}
+	else if (wacom->touch_input) {
 		dev_dbg(wacom->touch_input->dev.parent,
 			"%s: received report #%d\n", __func__, data[0]);
 
-	switch (len) {
-	case WACOM_PKGLEN_TPC1FG:
-		return wacom_tpc_single_touch(wacom, len);
-
-	case WACOM_PKGLEN_TPC2FG:
-		return wacom_tpc_mt_touch(wacom);
-
-	case WACOM_PKGLEN_PENABLED:
-		return wacom_tpc_pen(wacom);
-
-	default:
-		switch (data[0]) {
-		case WACOM_REPORT_TPC1FG:
-		case WACOM_REPORT_TPCHID:
-		case WACOM_REPORT_TPCST:
-		case WACOM_REPORT_TPC1FGE:
+		switch (len) {
+		case WACOM_PKGLEN_TPC1FG:
 			return wacom_tpc_single_touch(wacom, len);
 
-		case WACOM_REPORT_TPCMT:
-		case WACOM_REPORT_TPCMT2:
-			return wacom_mt_touch(wacom);
+		case WACOM_PKGLEN_TPC2FG:
+			return wacom_tpc_mt_touch(wacom);
 
-		case WACOM_REPORT_PENABLED:
-			return wacom_tpc_pen(wacom);
+		default:
+			switch (data[0]) {
+			case WACOM_REPORT_TPC1FG:
+			case WACOM_REPORT_TPCHID:
+			case WACOM_REPORT_TPCST:
+			case WACOM_REPORT_TPC1FGE:
+				return wacom_tpc_single_touch(wacom, len);
+
+			case WACOM_REPORT_TPCMT:
+			case WACOM_REPORT_TPCMT2:
+				return wacom_mt_touch(wacom);
+
+			}
 		}
 	}
 

drivers/i2c/busses/i2c-tiny-usb.c

@@ -178,22 +178,39 @@ static int usb_read(struct i2c_adapter *adapter, int cmd,
 		    int value, int index, void *data, int len)
 {
 	struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+	void *dmadata = kmalloc(len, GFP_KERNEL);
+	int ret;
+
+	if (!dmadata)
+		return -ENOMEM;
 
 	/* do control transfer */
-	return usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
+	ret = usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
 			       cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE |
-			       USB_DIR_IN, value, index, data, len, 2000);
+			       USB_DIR_IN, value, index, dmadata, len, 2000);
+
+	memcpy(data, dmadata, len);
+	kfree(dmadata);
+	return ret;
 }
 
 static int usb_write(struct i2c_adapter *adapter, int cmd,
 		     int value, int index, void *data, int len)
 {
 	struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+	void *dmadata = kmemdup(data, len, GFP_KERNEL);
+	int ret;
+
+	if (!dmadata)
+		return -ENOMEM;
 
 	/* do control transfer */
-	return usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
+	ret = usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
 			       cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
-			       value, index, data, len, 2000);
+			       value, index, dmadata, len, 2000);
+
+	kfree(dmadata);
+	return ret;
 }
 
 static void i2c_tiny_usb_free(struct i2c_tiny_usb *dev)

drivers/infiniband/hw/hfi1/rc.c

@@ -2366,8 +2366,11 @@ send_last:
 		ret = hfi1_rvt_get_rwqe(qp, 1);
 		if (ret < 0)
 			goto nack_op_err;
-		if (!ret)
+		if (!ret) {
+			/* peer will send again */
+			rvt_put_ss(&qp->r_sge);
 			goto rnr_nak;
+		}
 		wc.ex.imm_data = ohdr->u.rc.imm_data;
 		wc.wc_flags = IB_WC_WITH_IMM;
 		goto send_last;

drivers/infiniband/hw/qib/qib_rc.c

@@ -2067,8 +2067,10 @@ send_last:
 		ret = qib_get_rwqe(qp, 1);
 		if (ret < 0)
 			goto nack_op_err;
-		if (!ret)
+		if (!ret) {
+			rvt_put_ss(&qp->r_sge);
 			goto rnr_nak;
+		}
 		wc.ex.imm_data = ohdr->u.rc.imm_data;
 		hdrsize += 4;
 		wc.wc_flags = IB_WC_WITH_IMM;

drivers/misc/Kconfig

@@ -776,7 +776,7 @@ config PANEL_BOOT_MESSAGE
 
 config UID_SYS_STATS
 	bool "Per-UID statistics"
-	depends on PROFILING
+	depends on PROFILING && TASK_XACCT && TASK_IO_ACCOUNTING
 	help
 	  Per UID based cpu time statistics exported to /proc/uid_cputime
 	  Per UID based io statistics exported to /proc/uid_io

drivers/mmc/host/sdhci-iproc.c

@@ -157,7 +157,8 @@ static const struct sdhci_ops sdhci_iproc_ops = {
 };
 
 static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = {
-	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
+	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+		  SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
 	.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN,
 	.ops = &sdhci_iproc_ops,
 };

drivers/net/bonding/bond_3ad.c

@@ -2573,7 +2573,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond,
 		return -1;
 
 	ad_info->aggregator_id = aggregator->aggregator_identifier;
-	ad_info->ports = aggregator->num_of_ports;
+	ad_info->ports = __agg_active_ports(aggregator);
 	ad_info->actor_key = aggregator->actor_oper_aggregator_key;
 	ad_info->partner_key = aggregator->partner_oper_aggregator_key;
 	ether_addr_copy(ad_info->partner_system,

drivers/net/ethernet/emulex/benet/be_main.c

@@ -5144,9 +5144,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
-	/* The code below restricts offload features for some tunneled packets.
+	/* The code below restricts offload features for some tunneled and
+	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.
 	 */
+	features = vlan_features_check(skb, features);
 	if (!skb->encapsulation ||
 	    !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
 		return features;

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -767,7 +767,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 		       mlx5_command_str(msg_to_opcode(ent->in)),
 		       msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
 static void cmd_work_handler(struct work_struct *work)
@@ -797,6 +797,7 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -818,6 +819,20 @@ static void cmd_work_handler(struct work_struct *work)
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
 
+	/* Skip sending command to fw if internal error */
+	if (pci_channel_offline(dev->pdev) ||
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		u8 status = 0;
+		u32 drv_synd;
+
+		ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
+		MLX5_SET(mbox_out, ent->out, status, status);
+		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
+
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		return;
+	}
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -828,7 +843,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -872,7 +887,7 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
 		ent->ret = -ETIMEDOUT;
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
 	err = ent->ret;
@@ -1369,7 +1384,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1389,6 +1404,19 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+
+			/* if we already completed the command, ignore it */
+			if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
+						&ent->state)) {
+				/* only real completion can free the cmd slot */
+				if (!forced) {
+					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
+						      ent->idx);
+					free_ent(cmd, ent->idx);
+				}
+				continue;
+			}
+
 			if (ent->callback)
 				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
@@ -1411,7 +1439,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 				mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
 					      ent->ret, deliv_status_to_str(ent->status), ent->status);
 			}
-			free_ent(cmd, ent->idx);
+
+			/* only real completion will free the entry slot */
+			if (!forced)
+				free_ent(cmd, ent->idx);
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;

drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c

@@ -751,7 +751,6 @@ static void get_supported(u32 eth_proto_cap,
 	ptys2ethtool_supported_port(link_ksettings, eth_proto_cap);
 	ptys2ethtool_supported_link(supported, eth_proto_cap);
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
-	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause);
 }
 
 static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
@@ -761,7 +760,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
 
 	ptys2ethtool_adver_link(advertising, eth_proto_cap);
-	if (tx_pause)
+	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause);
@@ -806,6 +805,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
+	u32 rx_pause = 0;
+	u32 tx_pause = 0;
 	u32 eth_proto_cap;
 	u32 eth_proto_admin;
 	u32 eth_proto_lp;
@@ -828,11 +829,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
 	an_status        = MLX5_GET(ptys_reg, out, an_status);
 
+	mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
 	get_supported(eth_proto_cap, link_ksettings);
-	get_advertising(eth_proto_admin, 0, 0, link_ksettings);
+	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
 	get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;

drivers/net/ethernet/mellanox/mlx5/core/eq.c

@@ -234,7 +234,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			break;
 
 		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
+			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
 			break;
 
 		case MLX5_EVENT_TYPE_PORT_CHANGE:

drivers/net/ethernet/mellanox/mlx5/core/health.c

@@ -90,7 +90,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 
 	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
 	return;
 
 no_trig:

drivers/net/phy/marvell.c

@@ -240,34 +240,6 @@ static int marvell_config_aneg(struct phy_device *phydev)
 {
 	int err;
 
-	/* The Marvell PHY has an errata which requires
-	 * that certain registers get written in order
-	 * to restart autonegotiation */
-	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
-
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x1f);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x200c);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x5);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x100);
-	if (err < 0)
-		return err;
-
 	err = marvell_set_polarity(phydev, phydev->mdix);
 	if (err < 0)
 		return err;
@@ -301,6 +273,42 @@ static int marvell_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e1101_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	/* This Marvell PHY has an errata which requires
+	 * that certain registers get written in order
+	 * to restart autonegotiation
+	 */
+	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x1f);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x200c);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x5);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x100);
+	if (err < 0)
+		return err;
+
+	return marvell_config_aneg(phydev);
+}
+
 static int m88e1111_config_aneg(struct phy_device *phydev)
 {
 	int err;
@@ -1491,7 +1499,7 @@ static struct phy_driver marvell_drivers[] = {
 		.probe = marvell_probe,
 		.flags = PHY_HAS_INTERRUPT,
 		.config_init = &marvell_config_init,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1101_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,

drivers/net/usb/qmi_wwan.c

@@ -897,6 +897,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */

drivers/net/virtio_net.c

@@ -1456,6 +1456,7 @@ static const struct net_device_ops virtnet_netdev = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= virtnet_busy_poll,
 #endif
+	.ndo_features_check	= passthru_features_check,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)

drivers/net/vrf.c

@@ -850,6 +850,7 @@ static u32 vrf_fib_table(const struct net_device *dev)
 
 static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	kfree_skb(skb);
 	return 0;
 }
 
@@ -859,7 +860,7 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
 {
 	struct net *net = dev_net(dev);
 
-	if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
+	if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1)
 		skb = NULL;    /* kfree_skb(skb) handled by nf code */
 
 	return skb;

drivers/nvme/host/core.c

@@ -1725,7 +1725,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_attr_group);
 		del_gendisk(ns->disk);
-		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
 
@@ -2048,8 +2047,16 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 			continue;
 		revalidate_disk(ns->disk);
 		blk_set_queue_dying(ns->queue);
-		blk_mq_abort_requeue_list(ns->queue);
-		blk_mq_start_stopped_hw_queues(ns->queue, true);
+
+		/*
+		 * Forcibly start all queues to avoid having stuck requests.
+		 * Note that we must ensure the queues are not stopped
+		 * when the final removal happens.
+		 */
+		blk_mq_start_hw_queues(ns->queue);
+
+		/* draining requests in requeue list */
+		blk_mq_kick_requeue_list(ns->queue);
 	}
 	mutex_unlock(&ctrl->namespaces_mutex);
 }

drivers/nvme/host/rdma.c

@@ -1011,6 +1011,19 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 		nvme_rdma_wr_error(cq, wc, "SEND");
 }
 
+static inline int nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
+{
+	int sig_limit;
+
+	/*
+	 * We signal completion every queue depth/2 and also handle the
+	 * degenerated case of a  device with queue_depth=1, where we
+	 * would need to signal every message.
+	 */
+	sig_limit = max(queue->queue_size / 2, 1);
+	return (++queue->sig_count % sig_limit) == 0;
+}
+
 static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 		struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
 		struct ib_send_wr *first, bool flush)
@@ -1038,9 +1051,6 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	 * Would have been way to obvious to handle this in hardware or
 	 * at least the RDMA stack..
 	 *
-	 * This messy and racy code sniplet is copy and pasted from the iSER
-	 * initiator, and the magic '32' comes from there as well.
-	 *
 	 * Always signal the flushes. The magic request used for the flush
 	 * sequencer is not allocated in our driver's tagset and it's
 	 * triggered to be freed by blk_cleanup_queue(). So we need to
@@ -1048,7 +1058,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	 * embeded in request's payload, is not freed when __ib_process_cq()
 	 * calls wr_cqe->done().
 	 */
-	if ((++queue->sig_count % 32) == 0 || flush)
+	if (nvme_rdma_queue_sig_limit(queue) || flush)
 		wr.send_flags |= IB_SEND_SIGNALED;
 
 	if (first)

drivers/s390/net/qeth_core.h

@@ -718,6 +718,7 @@ enum qeth_discipline_id {
 };
 
 struct qeth_discipline {
+	const struct device_type *devtype;
 	void (*start_poll)(struct ccw_device *, int, unsigned long);
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
@@ -893,6 +894,9 @@ extern struct qeth_discipline qeth_l2_discipline;
 extern struct qeth_discipline qeth_l3_discipline;
 extern const struct attribute_group *qeth_generic_attr_groups[];
 extern const struct attribute_group *qeth_osn_attr_groups[];
+extern const struct attribute_group qeth_device_attr_group;
+extern const struct attribute_group qeth_device_blkt_group;
+extern const struct device_type qeth_generic_devtype;
 extern struct workqueue_struct *qeth_wq;
 
 int qeth_card_hw_is_reachable(struct qeth_card *);

drivers/s390/net/qeth_core_main.c

@@ -5462,10 +5462,12 @@ void qeth_core_free_discipline(struct qeth_card *card)
 	card->discipline = NULL;
 }
 
-static const struct device_type qeth_generic_devtype = {
+const struct device_type qeth_generic_devtype = {
 	.name = "qeth_generic",
 	.groups = qeth_generic_attr_groups,
 };
+EXPORT_SYMBOL_GPL(qeth_generic_devtype);
+
 static const struct device_type qeth_osn_devtype = {
 	.name = "qeth_osn",
 	.groups = qeth_osn_attr_groups,
@@ -5591,23 +5593,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		goto err_card;
 	}
 
-	if (card->info.type == QETH_CARD_TYPE_OSN)
-		gdev->dev.type = &qeth_osn_devtype;
-	else
-		gdev->dev.type = &qeth_generic_devtype;
-
 	switch (card->info.type) {
 	case QETH_CARD_TYPE_OSN:
 	case QETH_CARD_TYPE_OSM:
 		rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2);
 		if (rc)
 			goto err_card;
+
+		gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
+					? card->discipline->devtype
+					: &qeth_osn_devtype;
 		rc = card->discipline->setup(card->gdev);
 		if (rc)
 			goto err_disc;
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSX:
+		break;
 	default:
+		gdev->dev.type = &qeth_generic_devtype;
 		break;
 	}
 
@@ -5663,8 +5664,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
 		if (rc)
 			goto err;
 		rc = card->discipline->setup(card->gdev);
-		if (rc)
+		if (rc) {
+			qeth_core_free_discipline(card);
 			goto err;
+		}
 	}
 	rc = card->discipline->set_online(gdev);
 err:

drivers/s390/net/qeth_core_sys.c

@@ -413,12 +413,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 
 	if (card->options.layer2 == newdis)
 		goto out;
-	else {
-		card->info.mac_bits  = 0;
-		if (card->discipline) {
-			card->discipline->remove(card->gdev);
-			qeth_core_free_discipline(card);
-		}
+	if (card->info.type == QETH_CARD_TYPE_OSM) {
+		/* fixed layer, can't switch */
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	card->info.mac_bits = 0;
+	if (card->discipline) {
+		card->discipline->remove(card->gdev);
+		qeth_core_free_discipline(card);
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
@@ -426,6 +430,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		goto out;
 
 	rc = card->discipline->setup(card->gdev);
+	if (rc)
+		qeth_core_free_discipline(card);
 out:
 	mutex_unlock(&card->discipline_mutex);
 	return rc ? rc : count;
@@ -703,10 +709,11 @@ static struct attribute *qeth_blkt_device_attrs[] = {
 	&dev_attr_inter_jumbo.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_blkt_group = {
+const struct attribute_group qeth_device_blkt_group = {
 	.name = "blkt",
 	.attrs = qeth_blkt_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_blkt_group);
 
 static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_state.attr,
@@ -726,9 +733,10 @@ static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_switch_attrs.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_attr_group = {
+const struct attribute_group qeth_device_attr_group = {
 	.attrs = qeth_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_attr_group);
 
 const struct attribute_group *qeth_generic_attr_groups[] = {
 	&qeth_device_attr_group,

drivers/s390/net/qeth_l2.h

@@ -8,6 +8,8 @@
 
 #include "qeth_core.h"
 
+extern const struct attribute_group *qeth_l2_attr_groups[];
+
 int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);

drivers/s390/net/qeth_l2_main.c

@@ -1021,11 +1021,21 @@ static int qeth_l2_stop(struct net_device *dev)
 	return 0;
 }
 
+static const struct device_type qeth_l2_devtype = {
+	.name = "qeth_layer2",
+	.groups = qeth_l2_attr_groups,
+};
+
 static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l2_create_device_attributes(&gdev->dev);
+	if (gdev->dev.type == &qeth_generic_devtype) {
+		rc = qeth_l2_create_device_attributes(&gdev->dev);
+		if (rc)
+			return rc;
+	}
 	INIT_LIST_HEAD(&card->vid_list);
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
@@ -1037,7 +1047,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
 
-	qeth_l2_remove_device_attributes(&cgdev->dev);
+	if (cgdev->dev.type == &qeth_generic_devtype)
+		qeth_l2_remove_device_attributes(&cgdev->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
@@ -1095,7 +1106,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	case QETH_CARD_TYPE_OSN:
 		card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
 					 ether_setup);
-		card->dev->flags |= IFF_NOARP;
 		break;
 	default:
 		card->dev = alloc_etherdev(0);
@@ -1108,9 +1118,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
-	card->dev->ethtool_ops =
-		(card->info.type != QETH_CARD_TYPE_OSN) ?
-		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
+	if (card->info.type == QETH_CARD_TYPE_OSN) {
+		card->dev->ethtool_ops = &qeth_l2_osn_ops;
+		card->dev->flags |= IFF_NOARP;
+	} else {
+		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+	}
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
@@ -1434,6 +1447,7 @@ static int qeth_l2_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l2_discipline = {
+	.devtype = &qeth_l2_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,

drivers/s390/net/qeth_l2_sys.c

@@ -272,3 +272,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
 	} else
 		qeth_bridgeport_an_set(card, 0);
 }
+
+const struct attribute_group *qeth_l2_attr_groups[] = {
+	&qeth_device_attr_group,
+	&qeth_device_blkt_group,
+	/* l2 specific, see l2_{create,remove}_device_attributes(): */
+	&qeth_l2_bridgeport_attr_group,
+	NULL,
+};

drivers/s390/net/qeth_l3_main.c

@@ -3157,8 +3157,13 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l3_create_device_attributes(&gdev->dev);
+	rc = qeth_l3_create_device_attributes(&gdev->dev);
+	if (rc)
+		return rc;
+	hash_init(card->ip_htable);
+	hash_init(card->ip_mc_htable);
 	card->options.layer2 = 0;
 	card->info.hwtrap = 0;
 	return 0;
@@ -3450,6 +3455,7 @@ static int qeth_l3_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l3_discipline = {
+	.devtype = &qeth_generic_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,

drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c

@@ -1169,6 +1169,8 @@ static struct ibmvscsis_cmd *ibmvscsis_get_free_cmd(struct scsi_info *vscsi)
 		cmd = list_first_entry_or_null(&vscsi->free_cmd,
 					       struct ibmvscsis_cmd, list);
 		if (cmd) {
+			if (cmd->abort_cmd)
+				cmd->abort_cmd = NULL;
 			cmd->flags &= ~(DELAY_SEND);
 			list_del(&cmd->list);
 			cmd->iue = iue;
@@ -1773,6 +1775,7 @@ static void ibmvscsis_send_messages(struct scsi_info *vscsi)
 				if (cmd->abort_cmd) {
 					retry = true;
 					cmd->abort_cmd->flags &= ~(DELAY_SEND);
+					cmd->abort_cmd = NULL;
 				}
 
 				/*
@@ -1787,6 +1790,25 @@ static void ibmvscsis_send_messages(struct scsi_info *vscsi)
 					list_del(&cmd->list);
 					ibmvscsis_free_cmd_resources(vscsi,
 								     cmd);
+					/*
+					 * With a successfully aborted op
+					 * through LIO we want to increment the
+					 * the vscsi credit so that when we dont
+					 * send a rsp to the original scsi abort
+					 * op (h_send_crq), but the tm rsp to
+					 * the abort is sent, the credit is
+					 * correctly sent with the abort tm rsp.
+					 * We would need 1 for the abort tm rsp
+					 * and 1 credit for the aborted scsi op.
+					 * Thus we need to increment here.
+					 * Also we want to increment the credit
+					 * here because we want to make sure
+					 * cmd is actually released first
+					 * otherwise the client will think it
+					 * it can send a new cmd, and we could
+					 * find ourselves short of cmd elements.
+					 */
+					vscsi->credit += 1;
 				} else {
 					iue = cmd->iue;
 
@@ -2961,10 +2983,7 @@ static long srp_build_response(struct scsi_info *vscsi,
 
 	rsp->opcode = SRP_RSP;
 
-	if (vscsi->credit > 0 && vscsi->state == SRP_PROCESSING)
-		rsp->req_lim_delta = cpu_to_be32(vscsi->credit);
-	else
-		rsp->req_lim_delta = cpu_to_be32(1 + vscsi->credit);
+	rsp->req_lim_delta = cpu_to_be32(1 + vscsi->credit);
 	rsp->tag = cmd->rsp.tag;
 	rsp->flags = 0;
 

drivers/scsi/mpt3sas/mpt3sas_scsih.c

@@ -4634,6 +4634,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
+	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
@@ -4692,6 +4693,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+	/* In case of bogus fw or device, we could end up having
+	 * unaligned partial completion. We can force alignment here,
+	 * then scsi-ml does not need to handle this misbehavior.
+	 */
+	sector_sz = scmd->device->sector_size;
+	if (unlikely(scmd->request->cmd_type == REQ_TYPE_FS && sector_sz &&
+		     xfer_cnt % sector_sz)) {
+		sdev_printk(KERN_INFO, scmd->device,
+		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+			    xfer_cnt, sector_sz);
+		xfer_cnt = round_down(xfer_cnt, sector_sz);
+	}
+
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);

drivers/target/iscsi/iscsi_target.c

@@ -3798,6 +3798,8 @@ int iscsi_target_tx_thread(void *arg)
 {
 	int ret = 0;
 	struct iscsi_conn *conn = arg;
+	bool conn_freed = false;
+
 	/*
 	 * Allow ourselves to be interrupted by SIGINT so that a
 	 * connection recovery / failure event can be triggered externally.
@@ -3823,12 +3825,14 @@ get_immediate:
 			goto transport_err;
 
 		ret = iscsit_handle_response_queue(conn);
-		if (ret == 1)
+		if (ret == 1) {
 			goto get_immediate;
-		else if (ret == -ECONNRESET)
+		} else if (ret == -ECONNRESET) {
+			conn_freed = true;
 			goto out;
-		else if (ret < 0)
+		} else if (ret < 0) {
 			goto transport_err;
+		}
 	}
 
 transport_err:
@@ -3838,8 +3842,13 @@ transport_err:
 	 * responsible for cleaning up the early connection failure.
 	 */
 	if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
-		iscsit_take_action_for_connection_exit(conn);
+		iscsit_take_action_for_connection_exit(conn, &conn_freed);
 out:
+	if (!conn_freed) {
+		while (!kthread_should_stop()) {
+			msleep(100);
+		}
+	}
 	return 0;
 }
 
@@ -4012,6 +4021,7 @@ int iscsi_target_rx_thread(void *arg)
 {
 	int rc;
 	struct iscsi_conn *conn = arg;
+	bool conn_freed = false;
 
 	/*
 	 * Allow ourselves to be interrupted by SIGINT so that a
@@ -4024,7 +4034,7 @@ int iscsi_target_rx_thread(void *arg)
 	 */
 	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
 	if (rc < 0 || iscsi_target_check_conn_state(conn))
-		return 0;
+		goto out;
 
 	if (!conn->conn_transport->iscsit_get_rx_pdu)
 		return 0;
@@ -4033,7 +4043,15 @@ int iscsi_target_rx_thread(void *arg)
 
 	if (!signal_pending(current))
 		atomic_set(&conn->transport_failed, 1);
-	iscsit_take_action_for_connection_exit(conn);
+	iscsit_take_action_for_connection_exit(conn, &conn_freed);
+
+out:
+	if (!conn_freed) {
+		while (!kthread_should_stop()) {
+			msleep(100);
+		}
+	}
+
 	return 0;
 }
 

drivers/target/iscsi/iscsi_target_erl0.c

@@ -930,8 +930,10 @@ static void iscsit_handle_connection_cleanup(struct iscsi_conn *conn)
 	}
 }
 
-void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
+void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn, bool *conn_freed)
 {
+	*conn_freed = false;
+
 	spin_lock_bh(&conn->state_lock);
 	if (atomic_read(&conn->connection_exit)) {
 		spin_unlock_bh(&conn->state_lock);
@@ -942,6 +944,7 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
 	if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) {
 		spin_unlock_bh(&conn->state_lock);
 		iscsit_close_connection(conn);
+		*conn_freed = true;
 		return;
 	}
 
@@ -955,4 +958,5 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
 	spin_unlock_bh(&conn->state_lock);
 
 	iscsit_handle_connection_cleanup(conn);
+	*conn_freed = true;
 }

drivers/target/iscsi/iscsi_target_erl0.h

@@ -9,6 +9,6 @@ extern int iscsit_stop_time2retain_timer(struct iscsi_session *);
 extern void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *);
 extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int);
 extern void iscsit_fall_back_to_erl0(struct iscsi_session *);
-extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *);
+extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *, bool *);
 
 #endif   /*** ISCSI_TARGET_ERL0_H ***/

drivers/target/iscsi/iscsi_target_login.c

@@ -1460,5 +1460,9 @@ int iscsi_target_login_thread(void *arg)
 			break;
 	}
 
+	while (!kthread_should_stop()) {
+		msleep(100);
+	}
+
 	return 0;
 }

drivers/tty/serial/8250/8250_port.c

@@ -1320,7 +1320,7 @@ out_lock:
 	/*
 	 * Check if the device is a Fintek F81216A
 	 */
-	if (port->type == PORT_16550A)
+	if (port->type == PORT_16550A && port->iotype == UPIO_PORT)
 		fintek_8250_probe(up);
 
 	if (up->capabilities != old_capabilities) {

fs/f2fs/segment.c

@@ -1805,6 +1805,8 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 
 static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 {
+	struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal;
+	struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal;
 	int type = CURSEG_HOT_DATA;
 	int err;
 
@@ -1831,6 +1833,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 			return err;
 	}
 
+	/* sanity check for summary blocks */
+	if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
+			sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES)
+		return -EINVAL;
+
 	return 0;
 }
 

fs/f2fs/super.c

@@ -1424,6 +1424,8 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned int main_segs, blocks_per_seg;
+	int i;
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -1435,6 +1437,22 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	if (unlikely(fsmeta >= total))
 		return 1;
 
+	main_segs = le32_to_cpu(sbi->raw_super->segment_count_main);
+	blocks_per_seg = sbi->blocks_per_seg;
+
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
+		    le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) {
+			return 1;
+		}
+	}
+	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
+		    le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) {
+			return 1;
+		}
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;

fs/pnode.c

@@ -504,9 +504,14 @@ static struct mount *next_descendent(struct mount *root, struct mount *cur)
 	if (!IS_MNT_NEW(cur) && !list_empty(&cur->mnt_slave_list))
 		return first_slave(cur);
 	do {
-		if (cur->mnt_slave.next != &cur->mnt_master->mnt_slave_list)
-			return next_slave(cur);
-		cur = cur->mnt_master;
+		struct mount *master = cur->mnt_master;
+
+		if (!master || cur->mnt_slave.next != &master->mnt_slave_list) {
+			struct mount *next = next_slave(cur);
+
+			return (next == root) ? NULL : next;
+		}
+		cur = master;
 	} while (cur != root);
 	return NULL;
 }

fs/ufs/super.c

@@ -812,9 +812,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	uspi->s_dirblksize = UFS_SECTOR_SIZE;
 	super_block_offset=UFS_SBLOCK;
 
-	/* Keep 2Gig file limit. Some UFS variants need to override 
-	   this but as I don't know which I'll let those in the know loosen
-	   the rules */
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
 	switch (sbi->s_mount_opt & UFS_MOUNT_UFSTYPE) {
 	case UFS_MOUNT_UFSTYPE_44BSD:
 		UFSD("ufstype=44bsd\n");

fs/xfs/libxfs/xfs_bmap.c

@@ -2208,8 +2208,10 @@ xfs_bmap_add_extent_delay_real(
 		}
 		temp = xfs_bmap_worst_indlen(bma->ip, temp);
 		temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
-		diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
-			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
+		diff = (int)(temp + temp2 -
+			     (startblockval(PREV.br_startblock) -
+			      (bma->cur ?
+			       bma->cur->bc_private.b.allocated : 0)));
 		if (diff > 0) {
 			error = xfs_mod_fdblocks(bma->ip->i_mount,
 						 -((int64_t)diff), false);
@@ -2266,7 +2268,6 @@ xfs_bmap_add_extent_delay_real(
 		temp = da_new;
 		if (bma->cur)
 			temp += bma->cur->bc_private.b.allocated;
-		ASSERT(temp <= da_old);
 		if (temp < da_old)
 			xfs_mod_fdblocks(bma->ip->i_mount,
 					(int64_t)(da_old - temp), false);
@@ -3964,7 +3965,7 @@ xfs_bmap_remap_alloc(
 {
 	struct xfs_trans	*tp = ap->tp;
 	struct xfs_mount	*mp = tp->t_mountp;
-	xfs_agblock_t		bno;
+	xfs_fsblock_t		bno;
 	struct xfs_alloc_arg	args;
 	int			error;
 

fs/xfs/libxfs/xfs_btree.c

@@ -4376,7 +4376,7 @@ xfs_btree_visit_blocks(
 			xfs_btree_readahead_ptr(cur, ptr, 1);
 
 			/* save for the next iteration of the loop */
-			lptr = *ptr;
+			xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
 		}
 
 		/* for each buffer in the level */

fs/xfs/libxfs/xfs_dir2_priv.h

@@ -126,6 +126,7 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
 extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
+extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
 
 /* xfs_dir2_readdir.c */
 extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,

fs/xfs/libxfs/xfs_dir2_sf.c

@@ -629,6 +629,112 @@ xfs_dir2_sf_check(
 }
 #endif	/* DEBUG */
 
+/* Verify the consistency of an inline directory. */
+int
+xfs_dir2_sf_verify(
+	struct xfs_inode		*ip)
+{
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_dir2_sf_hdr		*sfp;
+	struct xfs_dir2_sf_entry	*sfep;
+	struct xfs_dir2_sf_entry	*next_sfep;
+	char				*endp;
+	const struct xfs_dir_ops	*dops;
+	struct xfs_ifork		*ifp;
+	xfs_ino_t			ino;
+	int				i;
+	int				i8count;
+	int				offset;
+	int				size;
+	int				error;
+	__uint8_t			filetype;
+
+	ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
+	/*
+	 * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops,
+	 * so we can only trust the mountpoint to have the right pointer.
+	 */
+	dops = xfs_dir_get_ops(mp, NULL);
+
+	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+	size = ifp->if_bytes;
+
+	/*
+	 * Give up if the directory is way too short.
+	 */
+	if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) ||
+	    size < xfs_dir2_sf_hdr_size(sfp->i8count))
+		return -EFSCORRUPTED;
+
+	endp = (char *)sfp + size;
+
+	/* Check .. entry */
+	ino = dops->sf_get_parent_ino(sfp);
+	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
+	error = xfs_dir_ino_validate(mp, ino);
+	if (error)
+		return error;
+	offset = dops->data_first_offset;
+
+	/* Check all reported entries */
+	sfep = xfs_dir2_sf_firstentry(sfp);
+	for (i = 0; i < sfp->count; i++) {
+		/*
+		 * struct xfs_dir2_sf_entry has a variable length.
+		 * Check the fixed-offset parts of the structure are
+		 * within the data buffer.
+		 */
+		if (((char *)sfep + sizeof(*sfep)) >= endp)
+			return -EFSCORRUPTED;
+
+		/* Don't allow names with known bad length. */
+		if (sfep->namelen == 0)
+			return -EFSCORRUPTED;
+
+		/*
+		 * Check that the variable-length part of the structure is
+		 * within the data buffer.  The next entry starts after the
+		 * name component, so nextentry is an acceptable test.
+		 */
+		next_sfep = dops->sf_nextentry(sfp, sfep);
+		if (endp < (char *)next_sfep)
+			return -EFSCORRUPTED;
+
+		/* Check that the offsets always increase. */
+		if (xfs_dir2_sf_get_offset(sfep) < offset)
+			return -EFSCORRUPTED;
+
+		/* Check the inode number. */
+		ino = dops->sf_get_ino(sfp, sfep);
+		i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
+		error = xfs_dir_ino_validate(mp, ino);
+		if (error)
+			return error;
+
+		/* Check the file type. */
+		filetype = dops->sf_get_ftype(sfep);
+		if (filetype >= XFS_DIR3_FT_MAX)
+			return -EFSCORRUPTED;
+
+		offset = xfs_dir2_sf_get_offset(sfep) +
+				dops->data_entsize(sfep->namelen);
+
+		sfep = next_sfep;
+	}
+	if (i8count != sfp->i8count)
+		return -EFSCORRUPTED;
+	if ((void *)sfep != (void *)endp)
+		return -EFSCORRUPTED;
+
+	/* Make sure this whole thing ought to be in local format. */
+	if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+	    (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
 /*
  * Create a new (shortform) directory.
  */

fs/xfs/libxfs/xfs_inode_fork.c

@@ -33,6 +33,8 @@
 #include "xfs_trace.h"
 #include "xfs_attr_sf.h"
 #include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
 
 kmem_zone_t *xfs_ifork_zone;
 
@@ -210,6 +212,16 @@ xfs_iformat_fork(
 	if (error)
 		return error;
 
+	/* Check inline dir contents. */
+	if (S_ISDIR(VFS_I(ip)->i_mode) &&
+	    dip->di_format == XFS_DINODE_FMT_LOCAL) {
+		error = xfs_dir2_sf_verify(ip);
+		if (error) {
+			xfs_idestroy_fork(ip, XFS_DATA_FORK);
+			return error;
+		}
+	}
+
 	if (xfs_is_reflink_inode(ip)) {
 		ASSERT(ip->i_cowfp == NULL);
 		xfs_ifork_init_cow(ip);
@@ -320,7 +332,6 @@ xfs_iformat_local(
 	int		whichfork,
 	int		size)
 {
-
 	/*
 	 * If the size is unreasonable, then something
 	 * is wrong and we just bail out rather than crash in

fs/xfs/libxfs/xfs_refcount.c

@@ -1629,13 +1629,28 @@ xfs_refcount_recover_cow_leftovers(
 	if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
 		return -EOPNOTSUPP;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	INIT_LIST_HEAD(&debris);
+
+	/*
+	 * In this first part, we use an empty transaction to gather up
+	 * all the leftover CoW extents so that we can subsequently
+	 * delete them.  The empty transaction is used to avoid
+	 * a buffer lock deadlock if there happens to be a loop in the
+	 * refcountbt because we're allowed to re-grab a buffer that is
+	 * already attached to our transaction.  When we're done
+	 * recording the CoW debris we cancel the (empty) transaction
+	 * and everything goes away cleanly.
+	 */
+	error = xfs_trans_alloc_empty(mp, &tp);
 	if (error)
 		return error;
-	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
+
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+	if (error)
+		goto out_trans;
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	/* Find all the leftover CoW staging extents. */
-	INIT_LIST_HEAD(&debris);
 	memset(&low, 0, sizeof(low));
 	memset(&high, 0, sizeof(high));
 	low.rc.rc_startblock = XFS_REFC_COW_START;
@@ -1645,10 +1660,11 @@ xfs_refcount_recover_cow_leftovers(
 	if (error)
 		goto out_cursor;
 	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
+	xfs_trans_cancel(tp);
 
 	/* Now iterate the list to free the leftovers */
-	list_for_each_entry(rr, &debris, rr_list) {
+	list_for_each_entry_safe(rr, n, &debris, rr_list) {
 		/* Set up transaction. */
 		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
 		if (error)
@@ -1676,8 +1692,16 @@ xfs_refcount_recover_cow_leftovers(
 		error = xfs_trans_commit(tp);
 		if (error)
 			goto out_free;
+
+		list_del(&rr->rr_list);
+		kmem_free(rr);
 	}
 
+	return error;
+out_defer:
+	xfs_defer_cancel(&dfops);
+out_trans:
+	xfs_trans_cancel(tp);
 out_free:
 	/* Free the leftover list */
 	list_for_each_entry_safe(rr, n, &debris, rr_list) {
@@ -1688,11 +1712,6 @@ out_free:
 
 out_cursor:
 	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_buf_relse(agbp);
-	goto out_free;
-
-out_defer:
-	xfs_defer_cancel(&dfops);
-	xfs_trans_cancel(tp);
-	goto out_free;
+	xfs_trans_brelse(tp, agbp);
+	goto out_trans;
 }

fs/xfs/libxfs/xfs_trans_space.h

@@ -21,8 +21,20 @@
 /*
  * Components of space reservations.
  */
+
+/* Worst case number of rmaps that can be held in a block. */
 #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
+
+/* Adding one rmap could split every level up to the top of the tree. */
+#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
+
+/* Blocks we might need to add "b" rmaps to a tree. */
+#define XFS_NRMAPADD_SPACE_RES(mp, b)\
+	(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
+	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
+	  XFS_RMAPADD_SPACE_RES(mp))
+
 #define XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)    \
 		(((mp)->m_alloc_mxr[0]) - ((mp)->m_alloc_mnr[0]))
 #define	XFS_EXTENTADD_SPACE_RES(mp,w)	(XFS_BM_MAXLEVELS(mp,w) - 1)
@@ -30,13 +42,12 @@
 	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
 	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
 	  XFS_EXTENTADD_SPACE_RES(mp,w))
+
+/* Blocks we might need to add "b" mappings & rmappings to a file. */
 #define XFS_SWAP_RMAP_SPACE_RES(mp,b,w)\
-	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
-	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
-	  XFS_EXTENTADD_SPACE_RES(mp,w) + \
-	 ((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
-	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
-	  (mp)->m_rmap_maxlevels)
+	(XFS_NEXTENTADD_SPACE_RES((mp), (b), (w)) + \
+	 XFS_NRMAPADD_SPACE_RES((mp), (b)))
+
 #define	XFS_DAENTER_1B(mp,w)	\
 	((w) == XFS_DATA_FORK ? (mp)->m_dir_geo->fsbcount : 1)
 #define	XFS_DAENTER_DBS(mp,w)	\

fs/xfs/xfs_aops.c

@@ -116,11 +116,11 @@ xfs_finish_page_writeback(
 
 	bsize = bh->b_size;
 	do {
+		if (off > end)
+			break;
 		next = bh->b_this_page;
 		if (off < bvec->bv_offset)
 			goto next_bh;
-		if (off > end)
-			break;
 		bh->b_end_io(bh, !error);
 next_bh:
 		off += bsize;

fs/xfs/xfs_bmap_item.c

@@ -34,6 +34,8 @@
 #include "xfs_bmap.h"
 #include "xfs_icache.h"
 #include "xfs_trace.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
 
 
 kmem_zone_t	*xfs_bui_zone;
@@ -446,7 +448,8 @@ xfs_bui_recover(
 		return -EIO;
 	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
+			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
 	if (error)
 		return error;
 	budp = xfs_trans_get_bud(tp, buip);

fs/xfs/xfs_bmap_util.c

@@ -588,9 +588,13 @@ xfs_getbmap(
 		}
 		break;
 	default:
+		/* Local format data forks report no extents. */
+		if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+			bmv->bmv_entries = 0;
+			return 0;
+		}
 		if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
-		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
-		    ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
+		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE)
 			return -EINVAL;
 
 		if (xfs_get_extsz_hint(ip) ||
@@ -718,7 +722,7 @@ xfs_getbmap(
 			 * extents.
 			 */
 			if (map[i].br_startblock == DELAYSTARTBLOCK &&
-			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+			    map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
 				ASSERT((iflags & BMV_IF_DELALLOC) != 0);
 
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
@@ -911,9 +915,9 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 }
 
 /*
- * This is called by xfs_inactive to free any blocks beyond eof
- * when the link count isn't zero and by xfs_dm_punch_hole() when
- * punching a hole to EOF.
+ * This is called to free any blocks beyond eof. The caller must hold
+ * IOLOCK_EXCL unless we are in the inode reclaim path and have the only
+ * reference to the inode.
  */
 int
 xfs_free_eofblocks(
@@ -928,8 +932,6 @@ xfs_free_eofblocks(
 	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
 
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-
 	/*
 	 * Figure out if there are any blocks beyond the end
 	 * of the file.  If not, then there is nothing to do.

fs/xfs/xfs_buf.c

@@ -96,27 +96,41 @@ static inline void
 xfs_buf_ioacct_inc(
 	struct xfs_buf	*bp)
 {
-	if (bp->b_flags & (XBF_NO_IOACCT|_XBF_IN_FLIGHT))
+	if (bp->b_flags & XBF_NO_IOACCT)
 		return;
 
 	ASSERT(bp->b_flags & XBF_ASYNC);
-	bp->b_flags |= _XBF_IN_FLIGHT;
-	percpu_counter_inc(&bp->b_target->bt_io_count);
+	spin_lock(&bp->b_lock);
+	if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) {
+		bp->b_state |= XFS_BSTATE_IN_FLIGHT;
+		percpu_counter_inc(&bp->b_target->bt_io_count);
+	}
+	spin_unlock(&bp->b_lock);
 }
 
 /*
  * Clear the in-flight state on a buffer about to be released to the LRU or
  * freed and unaccount from the buftarg.
  */
+static inline void
+__xfs_buf_ioacct_dec(
+	struct xfs_buf	*bp)
+{
+	ASSERT(spin_is_locked(&bp->b_lock));
+
+	if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
+		bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
+		percpu_counter_dec(&bp->b_target->bt_io_count);
+	}
+}
+
 static inline void
 xfs_buf_ioacct_dec(
 	struct xfs_buf	*bp)
 {
-	if (!(bp->b_flags & _XBF_IN_FLIGHT))
-		return;
-
-	bp->b_flags &= ~_XBF_IN_FLIGHT;
-	percpu_counter_dec(&bp->b_target->bt_io_count);
+	spin_lock(&bp->b_lock);
+	__xfs_buf_ioacct_dec(bp);
+	spin_unlock(&bp->b_lock);
 }
 
 /*
@@ -148,9 +162,9 @@ xfs_buf_stale(
 	 * unaccounted (released to LRU) before that occurs. Drop in-flight
 	 * status now to preserve accounting consistency.
 	 */
-	xfs_buf_ioacct_dec(bp);
-
 	spin_lock(&bp->b_lock);
+	__xfs_buf_ioacct_dec(bp);
+
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
 	    (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
@@ -953,12 +967,12 @@ xfs_buf_rele(
 		 * ensures the decrement occurs only once per-buf.
 		 */
 		if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru))
-			xfs_buf_ioacct_dec(bp);
+			__xfs_buf_ioacct_dec(bp);
 		goto out_unlock;
 	}
 
 	/* the last reference has been dropped ... */
-	xfs_buf_ioacct_dec(bp);
+	__xfs_buf_ioacct_dec(bp);
 	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
 		/*
 		 * If the buffer is added to the LRU take a new reference to the
@@ -1052,6 +1066,8 @@ void
 xfs_buf_unlock(
 	struct xfs_buf		*bp)
 {
+	ASSERT(xfs_buf_islocked(bp));
+
 	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
 
@@ -1789,6 +1805,28 @@ error:
 	return NULL;
 }
 
+/*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+void
+xfs_buf_delwri_cancel(
+	struct list_head	*list)
+{
+	struct xfs_buf		*bp;
+
+	while (!list_empty(list)) {
+		bp = list_first_entry(list, struct xfs_buf, b_list);
+
+		xfs_buf_lock(bp);
+		bp->b_flags &= ~_XBF_DELWRI_Q;
+		list_del_init(&bp->b_list);
+		xfs_buf_relse(bp);
+	}
+}
+
 /*
  * Add a buffer to the delayed write list.
  *

fs/xfs/xfs_buf.h

@@ -63,7 +63,6 @@ typedef enum {
 #define _XBF_KMEM	 (1 << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	 (1 << 22)/* buffer on a delwri queue */
 #define _XBF_COMPOUND	 (1 << 23)/* compound buffer */
-#define _XBF_IN_FLIGHT	 (1 << 25) /* I/O in flight, for accounting purposes */
 
 typedef unsigned int xfs_buf_flags_t;
 
@@ -83,14 +82,14 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
-	{ _XBF_COMPOUND,	"COMPOUND" }, \
-	{ _XBF_IN_FLIGHT,	"IN_FLIGHT" }
+	{ _XBF_COMPOUND,	"COMPOUND" }
 
 
 /*
  * Internal state flags.
  */
 #define XFS_BSTATE_DISPOSE	 (1 << 0)	/* buffer being discarded */
+#define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */
 
 /*
  * The xfs_buftarg contains 2 notions of "sector size" -
@@ -330,6 +329,7 @@ extern void *xfs_buf_offset(struct xfs_buf *, size_t);
 extern void xfs_buf_stale(struct xfs_buf *bp);
 
 /* Delayed Write Buffer Routines */
+extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);

fs/xfs/xfs_dir2_readdir.c

@@ -71,22 +71,11 @@ xfs_dir2_sf_getdents(
 	struct xfs_da_geometry	*geo = args->geo;
 
 	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	/*
-	 * Give up if the directory is way too short.
-	 */
-	if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
-		ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount));
-		return -EIO;
-	}
-
 	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 
-	if (dp->i_d.di_size < xfs_dir2_sf_hdr_size(sfp->i8count))
-		return -EFSCORRUPTED;
-
 	/*
 	 * If the block number in the offset is out of range, we're done.
 	 */
@@ -405,6 +394,7 @@ xfs_dir2_leaf_readbuf(
 
 	/*
 	 * Do we need more readahead?
+	 * Each loop tries to process 1 full dir blk; last may be partial.
 	 */
 	blk_start_plug(&plug);
 	for (mip->ra_index = mip->ra_offset = i = 0;
@@ -415,7 +405,8 @@ xfs_dir2_leaf_readbuf(
 		 * Read-ahead a contiguous directory block.
 		 */
 		if (i > mip->ra_current &&
-		    map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+		    (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
+		    geo->fsbcount) {
 			xfs_dir3_data_readahead(dp,
 				map[mip->ra_index].br_startoff + mip->ra_offset,
 				XFS_FSB_TO_DADDR(dp->i_mount,
@@ -436,14 +427,19 @@ xfs_dir2_leaf_readbuf(
 		}
 
 		/*
-		 * Advance offset through the mapping table.
+		 * Advance offset through the mapping table, processing a full
+		 * dir block even if it is fragmented into several extents.
+		 * But stop if we have consumed all valid mappings, even if
+		 * it's not yet a full directory block.
 		 */
-		for (j = 0; j < geo->fsbcount; j += length ) {
+		for (j = 0;
+		     j < geo->fsbcount && mip->ra_index < mip->map_valid;
+		     j += length ) {
 			/*
 			 * The rest of this extent but not more than a dir
 			 * block.
 			 */
-			length = min_t(int, geo->fsbcount,
+			length = min_t(int, geo->fsbcount - j,
 					map[mip->ra_index].br_blockcount -
 							mip->ra_offset);
 			mip->ra_offset += length;

fs/xfs/xfs_file.c

@@ -1130,13 +1130,13 @@ xfs_find_get_desired_pgoff(
 
 	index = startoff >> PAGE_SHIFT;
 	endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
-	end = endoff >> PAGE_SHIFT;
+	end = (endoff - 1) >> PAGE_SHIFT;
 	do {
 		int		want;
 		unsigned	nr_pages;
 		unsigned int	i;
 
-		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  want);
 		/*
@@ -1163,17 +1163,6 @@ xfs_find_get_desired_pgoff(
 			break;
 		}
 
-		/*
-		 * At lease we found one page.  If this is the first time we
-		 * step into the loop, and if the first page index offset is
-		 * greater than the given search offset, a hole was found.
-		 */
-		if (type == HOLE_OFF && lastoff == startoff &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = true;
-			break;
-		}
-
 		for (i = 0; i < nr_pages; i++) {
 			struct page	*page = pvec.pages[i];
 			loff_t		b_offset;
@@ -1185,18 +1174,18 @@ xfs_find_get_desired_pgoff(
 			 * file mapping. However, page->index will not change
 			 * because we have a reference on the page.
 			 *
-			 * Searching done if the page index is out of range.
-			 * If the current offset is not reaches the end of
-			 * the specified search range, there should be a hole
-			 * between them.
+			 * If current page offset is beyond where we've ended,
+			 * we've found a hole.
 			 */
-			if (page->index > end) {
-				if (type == HOLE_OFF && lastoff < endoff) {
-					*offset = lastoff;
-					found = true;
-				}
+			if (type == HOLE_OFF && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
+				found = true;
+				*offset = lastoff;
 				goto out;
 			}
+			/* Searching done if the page index is out of range. */
+			if (page->index > end)
+				goto out;
 
 			lock_page(page);
 			/*

fs/xfs/xfs_icache.c

@@ -264,6 +264,22 @@ xfs_inode_clear_reclaim_tag(
 	xfs_perag_clear_reclaim_tag(pag);
 }
 
+static void
+xfs_inew_wait(
+	struct xfs_inode	*ip)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
+	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
+
+	do {
+		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		if (!xfs_iflags_test(ip, XFS_INEW))
+			break;
+		schedule();
+	} while (true);
+	finish_wait(wq, &wait.wait);
+}
+
 /*
  * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
  * part of the structure. This is made more complex by the fact we store
@@ -368,14 +384,17 @@ xfs_iget_cache_hit(
 
 		error = xfs_reinit_inode(mp, inode);
 		if (error) {
+			bool wake;
 			/*
 			 * Re-initializing the inode failed, and we are in deep
 			 * trouble.  Try to re-add it to the reclaim list.
 			 */
 			rcu_read_lock();
 			spin_lock(&ip->i_flags_lock);
-
+			wake = !!__xfs_iflags_test(ip, XFS_INEW);
 			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+			if (wake)
+				wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 			ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
 			trace_xfs_iget_reclaim_fail(ip);
 			goto out_error;
@@ -625,9 +644,11 @@ out_error_or_again:
 
 STATIC int
 xfs_inode_ag_walk_grab(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	bool			newinos = !!(flags & XFS_AGITER_INEW_WAIT);
 
 	ASSERT(rcu_read_lock_held());
 
@@ -645,7 +666,8 @@ xfs_inode_ag_walk_grab(
 		goto out_unlock_noent;
 
 	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
-	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+	if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
+	    __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
 		goto out_unlock_noent;
 	spin_unlock(&ip->i_flags_lock);
 
@@ -673,7 +695,8 @@ xfs_inode_ag_walk(
 					   void *args),
 	int			flags,
 	void			*args,
-	int			tag)
+	int			tag,
+	int			iter_flags)
 {
 	uint32_t		first_index;
 	int			last_error = 0;
@@ -715,7 +738,7 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			struct xfs_inode *ip = batch[i];
 
-			if (done || xfs_inode_ag_walk_grab(ip))
+			if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
 				batch[i] = NULL;
 
 			/*
@@ -743,6 +766,9 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			if (!batch[i])
 				continue;
+			if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
+			    xfs_iflags_test(batch[i], XFS_INEW))
+				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
 			IRELE(batch[i]);
 			if (error == -EAGAIN) {
@@ -822,12 +848,13 @@ xfs_cowblocks_worker(
 }
 
 int
-xfs_inode_ag_iterator(
+xfs_inode_ag_iterator_flags(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
-	void			*args)
+	void			*args,
+	int			iter_flags)
 {
 	struct xfs_perag	*pag;
 	int			error = 0;
@@ -837,7 +864,8 @@ xfs_inode_ag_iterator(
 	ag = 0;
 	while ((pag = xfs_perag_get(mp, ag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
+					  iter_flags);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
@@ -848,6 +876,17 @@ xfs_inode_ag_iterator(
 	return last_error;
 }
 
+int
+xfs_inode_ag_iterator(
+	struct xfs_mount	*mp,
+	int			(*execute)(struct xfs_inode *ip, int flags,
+					   void *args),
+	int			flags,
+	void			*args)
+{
+	return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
+}
+
 int
 xfs_inode_ag_iterator_tag(
 	struct xfs_mount	*mp,
@@ -865,7 +904,8 @@ xfs_inode_ag_iterator_tag(
 	ag = 0;
 	while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
+					  0);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;

fs/xfs/xfs_icache.h

@@ -48,6 +48,11 @@ struct xfs_eofblocks {
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
 
+/*
+ * flags for AG inode iterator
+ */
+#define XFS_AGITER_INEW_WAIT	0x1	/* wait on new inodes */
+
 int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
 	     uint flags, uint lock_flags, xfs_inode_t **ipp);
 
@@ -79,6 +84,9 @@ void xfs_cowblocks_worker(struct work_struct *);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args);
+int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
+	int (*execute)(struct xfs_inode *ip, int flags, void *args),
+	int flags, void *args, int iter_flags);
 int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args, int tag);

fs/xfs/xfs_inode.c

@@ -50,6 +50,7 @@
 #include "xfs_log.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_dir2_priv.h"
 
 kmem_zone_t *xfs_inode_zone;
 
@@ -1914,12 +1915,13 @@ xfs_inactive(
 		 * force is true because we are evicting an inode from the
 		 * cache. Post-eof blocks must be freed, lest we end up with
 		 * broken free space accounting.
+		 *
+		 * Note: don't bother with iolock here since lockdep complains
+		 * about acquiring it in reclaim context. We have the only
+		 * reference to the inode at this point anyways.
 		 */
-		if (xfs_can_free_eofblocks(ip, true)) {
-			xfs_ilock(ip, XFS_IOLOCK_EXCL);
+		if (xfs_can_free_eofblocks(ip, true))
 			xfs_free_eofblocks(ip);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-		}
 
 		return;
 	}
@@ -3562,6 +3564,12 @@ xfs_iflush_int(
 	if (ip->i_d.di_version < 3)
 		ip->i_d.di_flushiter++;
 
+	/* Check the inline directory data. */
+	if (S_ISDIR(VFS_I(ip)->i_mode) &&
+	    ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
+	    xfs_dir2_sf_verify(ip))
+		goto corrupt_out;
+
 	/*
 	 * Copy the dirty parts of the inode into the on-disk inode.  We always
 	 * copy out the core of the inode, because if the inode is dirty at all

fs/xfs/xfs_inode.h

@@ -217,7 +217,8 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
 #define XFS_ISTALE		(1 << 1) /* inode has been staled */
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
-#define XFS_INEW		(1 << 3) /* inode has just been allocated */
+#define __XFS_INEW_BIT		3	 /* inode has just been allocated */
+#define XFS_INEW		(1 << __XFS_INEW_BIT)
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
 #define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
@@ -467,6 +468,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
 	xfs_iflags_clear(ip, XFS_INEW);
 	barrier();
 	unlock_new_inode(VFS_I(ip));
+	wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 }
 
 static inline void xfs_setup_existing_inode(struct xfs_inode *ip)

fs/xfs/xfs_ioctl.c

@@ -1542,10 +1542,11 @@ xfs_ioc_getbmap(
 	unsigned int		cmd,
 	void			__user *arg)
 {
-	struct getbmapx		bmx;
+	struct getbmapx		bmx = { 0 };
 	int			error;
 
-	if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
+	/* struct getbmap is a strict subset of struct getbmapx. */
+	if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags)))
 		return -EFAULT;
 
 	if (bmx.bmv_count < 2)

fs/xfs/xfs_iomap.c

@@ -1151,10 +1151,10 @@ xfs_xattr_iomap_begin(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	lockmode = xfs_ilock_data_map_shared(ip);
+	lockmode = xfs_ilock_attr_map_shared(ip);
 
 	/* if there are no attribute fork or extents, return ENOENT */
-	if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
+	if (!XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
 		error = -ENOENT;
 		goto out_unlock;
 	}

fs/xfs/xfs_itable.c

@@ -585,7 +585,7 @@ xfs_inumbers(
 		return error;
 
 	bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
-	buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+	buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
 	do {
 		struct xfs_inobt_rec_incore	r;
 		int				stat;

fs/xfs/xfs_log.c

@@ -1293,7 +1293,7 @@ void
 xfs_log_work_queue(
 	struct xfs_mount        *mp)
 {
-	queue_delayed_work(mp->m_log_workqueue, &mp->m_log->l_work,
+	queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work,
 				msecs_to_jiffies(xfs_syncd_centisecs * 10));
 }
 

fs/xfs/xfs_mount.h

@@ -183,6 +183,7 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_reclaim_workqueue;
 	struct workqueue_struct	*m_log_workqueue;
 	struct workqueue_struct *m_eofblocks_workqueue;
+	struct workqueue_struct	*m_sync_workqueue;
 
 	/*
 	 * Generation of the filesysyem layout.  This is incremented by each

fs/xfs/xfs_qm.c

@@ -1384,12 +1384,7 @@ xfs_qm_quotacheck(
 	mp->m_qflags |= flags;
 
  error_return:
-	while (!list_empty(&buffer_list)) {
-		struct xfs_buf *bp =
-			list_first_entry(&buffer_list, struct xfs_buf, b_list);
-		list_del_init(&bp->b_list);
-		xfs_buf_relse(bp);
-	}
+	xfs_buf_delwri_cancel(&buffer_list);
 
 	if (error) {
 		xfs_warn(mp,

fs/xfs/xfs_qm_syscalls.c

@@ -759,5 +759,6 @@ xfs_qm_dqrele_all_inodes(
 	uint		 flags)
 {
 	ASSERT(mp->m_quotainfo);
-	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL);
+	xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL,
+				    XFS_AGITER_INEW_WAIT);
 }

fs/xfs/xfs_reflink.c

@@ -736,8 +736,22 @@ xfs_reflink_end_cow(
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
 
-	/* Start a rolling transaction to switch the mappings */
-	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
+	/*
+	 * Start a rolling transaction to switch the mappings.  We're
+	 * unlikely ever to have to remap 16T worth of single-block
+	 * extents, so just cap the worst case extent count to 2^32-1.
+	 * Stick a warning in just in case, and avoid 64-bit division.
+	 */
+	BUILD_BUG_ON(MAX_RW_COUNT > UINT_MAX);
+	if (end_fsb - offset_fsb > UINT_MAX) {
+		error = -EFSCORRUPTED;
+		xfs_force_shutdown(ip->i_mount, SHUTDOWN_CORRUPT_INCORE);
+		ASSERT(0);
+		goto out;
+	}
+	resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount,
+			(unsigned int)(end_fsb - offset_fsb),
+			XFS_DATA_FORK);
 	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
 			resblks, 0, 0, &tp);
 	if (error)

fs/xfs/xfs_super.c

@@ -872,8 +872,15 @@ xfs_init_mount_workqueues(
 	if (!mp->m_eofblocks_workqueue)
 		goto out_destroy_log;
 
+	mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0,
+					       mp->m_fsname);
+	if (!mp->m_sync_workqueue)
+		goto out_destroy_eofb;
+
 	return 0;
 
+out_destroy_eofb:
+	destroy_workqueue(mp->m_eofblocks_workqueue);
 out_destroy_log:
 	destroy_workqueue(mp->m_log_workqueue);
 out_destroy_reclaim:
@@ -894,6 +901,7 @@ STATIC void
 xfs_destroy_mount_workqueues(
 	struct xfs_mount	*mp)
 {
+	destroy_workqueue(mp->m_sync_workqueue);
 	destroy_workqueue(mp->m_eofblocks_workqueue);
 	destroy_workqueue(mp->m_log_workqueue);
 	destroy_workqueue(mp->m_reclaim_workqueue);

fs/xfs/xfs_trans.c

@@ -262,6 +262,28 @@ xfs_trans_alloc(
 	return 0;
 }
 
+/*
+ * Create an empty transaction with no reservation.  This is a defensive
+ * mechanism for routines that query metadata without actually modifying
+ * them -- if the metadata being queried is somehow cross-linked (think a
+ * btree block pointer that points higher in the tree), we risk deadlock.
+ * However, blocks grabbed as part of a transaction can be re-grabbed.
+ * The verifiers will notice the corrupt block and the operation will fail
+ * back to userspace without deadlocking.
+ *
+ * Note the zero-length reservation; this transaction MUST be cancelled
+ * without any dirty data.
+ */
+int
+xfs_trans_alloc_empty(
+	struct xfs_mount		*mp,
+	struct xfs_trans		**tpp)
+{
+	struct xfs_trans_res		resv = {0};
+
+	return xfs_trans_alloc(mp, &resv, 0, 0, XFS_TRANS_NO_WRITECOUNT, tpp);
+}
+
 /*
  * Record the indicated change to the given field for application
  * to the file system's superblock when the transaction commits.